© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16505
    Prev
    Next
    INDEX
    Explanations

    references to action bars in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.69
     createState
    -0.66
    URLException
    -0.66
    帖最后由
    -0.64
    MemoryWarning
    -0.63
    jsxFileName
    -0.62
    wapV
    -0.62
     سكانية
    -0.62
    HostException
    -0.60
    RegressionTest
    -0.60
    POSITIVE LOGITS
    ActionBar
    2.14
     ActionBar
    1.52
    SupportActionBar
    1.10
     actionBar
    1.00
    actionBar
    0.99
     AppBar
    0.57
    appBar
    0.55
    ActionMode
    0.54
    OptionsMenu
    0.51
    Toolbar
    0.50
    Activations Density 0.000%

    No Known Activations